Support NeoGAF

[Unknown Quantity]

Google’s deep-learning program for determining the 3D shapes of proteins stands to transform biology, say scientists

An artificial intelligence (AI) network developed by Google AI offshoot DeepMind has made a gargantuan leap in solving one of biology’s grandest challenges — determining a protein’s 3D shape from its amino-acid sequence.

DeepMind’s program, called AlphaFold, outperformed around 100 other teams in a biennial protein-structure prediction challenge called CASP, short for Critical Assessment of Structure Prediction. The results were announced on 30 November, at the start of the conference — held virtually this year — that takes stock of the exercise.

“This is a big deal,” says John Moult, a computational biologist at the University of Maryland in College Park, who co-founded CASP in 1994 to improve computational methods for accurately predicting protein structures. “In some sense the problem is solved.”

‘It will change everything’: DeepMind’s AI makes gigantic leap in solving protein structures

Google’s deep-learning program for determining the 3D shapes of proteins stands to transform biology, say scientists.

www.nature.com

Sounds amazing. The more we understand about how they're formed we'll hopefully be building them in the near future.

 

[poodaddy]

This is one of the most exciting and important aspects of technological development to date. I'm not sure it will happen in my life time, but it's very possible that we may find a way to, if not necessarily cure it, then fight back against the exponential growth properties of cancer cells eventually, thus massively improving a patient's life span after a positive diagnosis. We've been saying fuck cancer for years, soon we may finally be able to truly fight it.

 

[Ozzy Onya A2Z]

It's all fun and games until AI learns to copyright its intellectual property in a stealth background task.

 

[Tschumi]

At what point is a dicky ai arm gonna emerge from my wall and swat a spoon of ice cream from my hand that's what i wanna know

 

[Chittagong]

This is massive, my biologist friends (Nature and Science published) tell me.

 

[eot]

Not directly relevant but sorta, good docu

 

[Unknown Quantity]

This is massive, my biologist friends (Nature and Science published) tell me.

They're at the beginning of something very exciting. It's taken 50 years or so to be able to solve the structure of 170000 enzymes of about 200 million proteins discovered across all lifeforms. With advancements in computing & machine learning speeding up, I can't wait. Read these articles, there's more info & it's good news in these silly times.

Science | AAAS

www.sciencemag.org

This is one of the most exciting and important aspects of technological development to date. I'm not sure it will happen in my life time, but it's very possible that we may find a way to, if not necessarily cure it, then fight back against the exponential growth properties of cancer cells eventually, thus massively improving a patient's life span after a positive diagnosis. We've been saying fuck cancer for years, soon we may finally be able to truly fight it.

"Even though one grand challenge has fallen, others will undoubtedly emerge. “This isn’t the end of something,” Thornton says. “It’s the beginning of many new things.”"

 

[eot]

 

[Bogey]

Not gonna lie - I have absolutely no idea what this could eventually be used for.

Are there any direct applications in the medical field or such?